Efficient Training papers, 2023–2026

Key findings

• Efficient Training went from 346 papers in 2023 to 603 in 2026, roughly 1.7x in three years.
• NeurIPS publishes the most Efficient Training work: 499 papers from 2023 to 2026, 28% of the four-venue total.
• The fastest-growing overlap is with Deep learning · large language models: papers tagged with both rose from 6 in 2023 to 50 in 2026.
• Among the 5 topics under Efficiency and Systems, it ranks #3 by 2026 paper count; the fastest grower in the group, Hardware-Aware ML, is up 4.4x versus 1.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
• ICML 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
• ICLR 2026An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation
• CVPR 2026A Bit is All You Need Efficient Video Capture via
• NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
• ICML 2025A Sample Efficient Conditional Independence Test in the Presence of Discretization
• ICLR 2025Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
• CVPR 2025Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024A fast algorithm to simulate nonlinear resistive networks
• ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
• CVPR 2024Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack
• NeurIPS 2023Alternating Updates for Efficient Transformers
• ICML 2023Auxiliary Modality Learning with Generalized Curriculum Distillation
• ICLR 2023A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
• CVPR 2023A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
• NeurIPS 2026Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
• ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
• ICLR 2026AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
• CVPR 2026Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning

All Efficient Training papers

516 papers, page 4 of 11

151. ICLR 2025HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging
152. ICLR 2025High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
153. ICLR 2025How efficient is LLM-generated code? A rigorous & high-standard benchmark
154. ICLR 2025Is uniform expressivity too restrictive? Towards efficient expressivity of GNNs
155. ICLR 2025Language models scale reliably with over-training and on downstream tasks
156. ICLR 2025Learning Efficient Positional Encodings with Graph Neural Networks
157. ICLR 2025LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions
158. ICLR 2025LiFT: Learning to Fine-Tune via Bayesian Parameter Efficient Meta Fine-Tuning
159. ICLR 2025LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
160. ICLR 2025LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth Efficiently
161. ICLR 2025MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba
162. ICLR 2025Memory Efficient Transformer Adapter for Dense Predictions
163. ICLR 2025Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
164. ICLR 2025MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
165. ICLR 2025MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
166. ICLR 2025Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning
167. ICLR 2025No Need to Talk: Asynchronous Mixture of Language Models
168. ICLR 2025Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
169. ICLR 2025Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
170. ICLR 2025ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
171. ICLR 2025One for all and all for one: Efficient computation of partial Wasserstein distances on the line
172. ICLR 2025Optimal Brain Apoptosis
173. ICLR 2025Pacmann: Efficient Private Approximate Nearest Neighbor Search
174. ICLR 2025PharmacoMatch: Efficient 3D Pharmacophore Screening via Neural Subgraph Matching
175. ICLR 2025Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
176. ICLR 2025PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
177. ICLR 2025PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing
178. ICLR 2025Preble: Efficient Distributed Prompt Scheduling for LLM Serving
179. ICLR 2025Progressive Mixed-Precision Decoding for Efficient LLM Inference
180. ICLR 2025Progressive Parameter Efficient Transfer Learning for Semantic Segmentation
181. ICLR 2025Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
182. ICLR 2025Quantum-PEFT: Ultra parameter-efficient fine-tuning
183. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
184. ICLR 2025Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
185. ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
186. ICLR 2025Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens
187. ICLR 2025Scaling Laws for Precision
188. ICLR 2025Scaling Optimal LR Across Token Horizons
189. ICLR 2025Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study
190. ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
191. ICLR 2025Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
192. ICLR 2025Skill Expansion and Composition in Parameter Space
193. ICLR 2025SONICS: Synthetic Or Not - Identifying Counterfeit Songs
194. ICLR 2025SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
195. ICLR 2025Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
196. ICLR 2025Structural-Entropy-Based Sample Selection for Efficient and Effective Learning
197. ICLR 2025Surprising Effectiveness of pretraining Ternary Language Model at Scale
198. ICLR 2025The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
199. ICLR 2025ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels
200. ICLR 2025TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

FAQ

How many Efficient Training papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,765 in total: 346 in 2023, 300 in 2024, 516 in 2025, 603 in 2026.

How many Efficient Training papers are at NeurIPS 2026?

NeurIPS 2026 has 177 Efficient Training papers, versus 190 the year before.

How many Efficient Training papers are at ICLR 2026?

ICLR 2026 has 148 Efficient Training papers, versus 126 the year before.

How many Efficient Training papers are at ICML 2026?

ICML 2026 has 169 Efficient Training papers, versus 118 the year before.

How many Efficient Training papers are at CVPR 2026?

CVPR 2026 has 109 Efficient Training papers, versus 82 the year before.

Which conference publishes the most Efficient Training papers?

NeurIPS, with 499 papers from 2023 to 2026.